arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.21902cs.CL
收藏

基于注意力模型和大语言模型提示的可解释法规预测

Explainable Statute Prediction via Attention-based Model and LLM Prompting

TCS Research(TCS研究)

Sachin Pawar, Girish Keshav Palshikar, Anindita Sinha Banerjee, Nitin Ramrakhiyani, Basit Ali

AI总结:

本文提出基于注意力模型和大语言模型提示的法规预测方法,通过生成可解释的预测结果提升法律AI系统的实用性。

摘要:

本文探讨了自动法规预测问题,即给定一个案件描述,预测相关法规的子集。这里的"法规"指任何特定法案中的条款、子条款或条文。解决这个问题在多个应用中都有用,例如为律师提供的AI助手和法律问题回答系统。为了更好地获得用户的接受,我们认为预测应伴随人类可理解的解释。我们提出了两种技术来解决带有解释的法规预测问题:(i) AoS(句子注意力),它使用案件描述中的句子注意力来预测相关的法规;(ii) LLMPrompt,它提示大语言模型预测并解释某一法规的相关性。AoS使用较小的语言模型,特别是句子转换器,并以监督方式训练,而LLMPrompt使用较大的语言模型以零样本方式训练,并探索标准以及链式推理(CoT)提示技术。这两种模型都以人类可理解的形式生成解释。我们比较了这两种技术在两个流行数据集上的法规预测性能,以及与一组竞争基线模型的性能。此外,我们通过自动化反事实方式以及通过人工评估来评估生成解释的质量。

英文摘要:

In this paper, we explore the problem of automatic statute prediction where for a given case description, a subset of relevant statutes are to be predicted. Here, the term "statute" refers to a section, a sub-section, or an article of any specific Act. Addressing this problem would be useful in several applications such as AI-assistant for lawyers and legal question answering system. For better user acceptance of such Legal AI systems, we believe the predictions should also be accompanied by human understandable explanations. We propose two techniques for addressing this problem of statute prediction with explanations -- (i) AoS (Attention-over-Sentences) which uses attention over sentences in a case description to predict statutes relevant for it and (ii) LLMPrompt which prompts an LLM to predict as well as explain relevance of a certain statute. AoS uses smaller language models, specifically sentence transformers and is trained in a supervised manner whereas LLMPrompt uses larger language models in a zero-shot manner and explores both standard as well as Chain-of-Thought (CoT) prompting techniques. Both these models produce explanations for their predictions in human understandable forms. We compare statute prediction performance of both the proposed techniques with each other as well as with a set of competent baselines, across two popular datasets. Also, we evaluate the quality of the generated explanations through an automated counter-factual manner as well as through human evaluation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑